© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143703
    Prev
    Next
    INDEX
    Explanations

    role, economic growth, survive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     espécies
    0.53
     triángulo
    0.50
     espécie
    0.47
    Sheets
    0.47
    ia
    0.46
     poseen
    0.46
     sabiduría
    0.45
    𝑢
    0.45
     batería
    0.45
    ów
    0.44
    POSITIVE LOGITS
     jobb
    0.47
    浚
    0.44
    笄
    0.44
    読んで
    0.43
    映像
    0.43
    逮捕
    0.43
    んで
    0.43
    تبه
    0.42
    景
    0.42
     Witnesses
    0.42
    Activations Density 0.002%

    No Known Activations